© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1164
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1.14
     D
    1.04
     n
    0.98
     T
    0.97
     N
    0.91
     V
    0.90
     P
    0.87
     v
    0.85
     J
    0.85
     W
    0.84
    POSITIVE LOGITS
    <unused957>
    1.19
     alkaloids
    1.17
    <unused1840>
    1.16
    oxylated
    1.16
    <unused1694>
    1.15
     स्क्यर
    1.13
     measurements
    1.11
    <unused433>
    1.10
     ointment
    1.10
     hematopoietic
    1.10
    Activations Density 0.677%

    No Known Activations